SOTAVerified

Image Generation

Image Generation (synthesis) is the task of generating new images from an existing dataset.

  • Unconditional generation refers to generating samples unconditionally from the dataset, i.e. $p(y)$
  • Conditional image generation (subtask) refers to generating samples conditionally from the dataset, based on a label, i.e. $p(y|x)$.

In this section, you can find state-of-the-art leaderboards for unconditional generation. For conditional generation, and other types of image generations, refer to the subtasks.

( Image credit: StyleGAN )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 3101–3150 of 6689 papers

TitleStatusHype
DreamSync: Aligning Text-to-Image Generation with Image Understanding Feedback—0
VBench: Comprehensive Benchmark Suite for Video Generative ModelsCode3
When StyleGAN Meets Stable Diffusion: a W_+ Adapter for Personalized Image GenerationCode1
Non-Visible Light Data Synthesis and Application: A Case Study for Synthetic Aperture Radar Imagery—0
SODA: Bottleneck Diffusion Models for Representation LearningCode1
HiDiffusion: Unlocking Higher-Resolution Creativity and Efficiency in Pretrained Diffusion Models—0
DiG-IN: Diffusion Guidance for Investigating Networks -- Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual ExplanationsCode1
Fair Text-to-Image Diffusion via Fair Mapping—0
Image Inpainting via Tractable Steering of Diffusion ModelsCode0
Unlocking Spatial Comprehension in Text-to-Image Diffusion Models—0
A High-Quality Robust Diffusion Framework for Corrupted DatasetCode0
Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image GenerationCode1
PEA-Diffusion: Parameter-Efficient Adapter with Knowledge Distillation in non-English Text-to-Image GenerationCode1
SEED-Bench-2: Benchmarking Multimodal Large Language ModelsCode2
Reason out Your Layout: Evoking the Layout Master from Large Language Models for Text-to-Image SynthesisCode1
Large Language Models Suffer From Their Own Output: An Analysis of the Self-Consuming Training Loop—0
Federated Learning with Diffusion Models for Privacy-Sensitive Vision TasksCode1
COLE: A Hierarchical Generation Framework for Multi-Layered and Editable Graphic Design—0
Text-Driven Image Editing via Learnable RegionsCode2
Adversarial Diffusion DistillationCode6
TextDiffuser-2: Unleashing the Power of Language Models for Text Rendering—0
MobileDiffusion: Instant Text-to-Image Generation on Mobile Devices—0
Denoising Diffusion Probabilistic Models for Image Inpainting of Cell Distributions in the Human Brain—0
Manifold Preserving Guided Diffusion—0
Enhancing Scene Text Detectors with Realistic Text Image Synthesis Using Diffusion ModelsCode1
Improving Denoising Diffusion Probabilistic Models via Exploiting Shared Representations—0
LLMGA: Multimodal Large Language Model based Generation AssistantCode2
Safe-CLIP: Removing NSFW Concepts from Vision-and-Language ModelsCode1
Pre-trained Language Models Do Not Help Auto-regressive Text-to-Image Generation—0
TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion ModelsCode1
VehicleGAN: Pair-flexible Pose Guided Image Synthesis for Vehicle Re-identification—0
Reinforcement Learning from Diffusion Feedback: Q* for Image Search—0
Check, Locate, Rectify: A Training-Free Layout Calibration System for Text-to-Image Generation—0
Direct2.5: Diverse Text-to-3D Generation via Multi-view 2.5D Diffusion—0
ViT-Lens: Towards Omni-modal RepresentationsCode1
PKU-I2IQA: An Image-to-Image Quality Assessment Database for AI Generated ImagesCode1
Learning Disentangled Identifiers for Action-Customized Text-to-Image Generation—0
Tell2Design: A Dataset for Language-Guided Floor Plan GenerationCode1
Self-correcting LLM-controlled Diffusion ModelsCode1
Street TryOn: Learning In-the-Wild Virtual Try-On from Unpaired Person ImagesCode1
ET3D: Efficient Text-to-3D Generation via Multi-View Distillation—0
BS-Diff: Effective Bone Suppression Using Conditional Diffusion Models from Chest X-Ray ImagesCode1
Flow-Guided Diffusion for Video InpaintingCode2
Automatic Synthetic Data and Fine-grained Adaptive Feature Alignment for Composed Person RetrievalCode1
Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large DatasetsCode0
Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual NoiseCode1
InstaStyle: Inversion Noise of a Stylized Image is Secretly a Style AdviserCode1
Synthetic Shifts to Initial Seed Vector Exposes the Brittle Nature of Latent-Based Diffusion Models—0
DemoFusion: Democratising High-Resolution Image Generation With No $Code4
AdaDiff: Adaptive Step Selection for Fast Diffusion Models—0
Show:102550
← PrevPage 63 of 134Next →
All datasetsImageNet 256x256CIFAR-10ImageNet 64x64ImageNet 512x512FFHQ 256 x 256CelebA 64x64ImageNet 32x32LSUN Bedroom 256 x 256STL-10LSUN Churches 256 x 256ImageNet 128x128FFHQ 1024 x 1024

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Improved DDPMFID12.3—Unverified
2ADMFID11.84—Unverified
3BigGAN-deepFID8.1—Unverified
4Polarity-BigGANFID6.82—Unverified
5VQGAN+Transformer (k=mixed, p=1.0, a=0.005)FID6.59—Unverified
6MaskGITFID6.18—Unverified
7VQGAN+Transformer (k=600, p=1.0, a=0.05)FID5.2—Unverified
8CDMFID4.88—Unverified
9ADM-GFID4.59—Unverified
10RINFID4.51—Unverified
#ModelMetricClaimedVerifiedStatus
1PresGANFID52.2—Unverified
2RESFLOWFID48.29—Unverified
3Residual FlowFID46.37—Unverified
4GLF+perceptual loss (ours)FID44.6—Unverified
5ProdPoly no activation functionsFID40.45—Unverified
6ProdPoly no activation functionsFID36.77—Unverified
7ACGANFID35.47—Unverified
8DenseFlow-74-10FID34.9—Unverified
9NVAE w/ flowFID32.53—Unverified
10QSNGANFID31.97—Unverified
#ModelMetricClaimedVerifiedStatus
1GLIDE + CLSFID30.87—Unverified
2GLIDE + CLIPFID30.46—Unverified
3GLIDE + CLS-FREEFID29.22—Unverified
4GLIDE + CLIP + CLS + CLS-FREEFID29.18—Unverified
5PGMGANFID21.73—Unverified
6CLR-GANFID20.27—Unverified
7FMFID14.45—Unverified
8CT (Direct Generation, NFE=1)FID13—Unverified
9CT (Direct Generation, NFE=2)FID11.1—Unverified
10GLIDE +CLSKID7.95—Unverified